© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63635
    Prev
    Next
    INDEX
    Explanations

    desert locations, Coachella

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⅜
    -0.69
    UseCase
    -0.65
    ianti
    -0.65
     preventing
    -0.63
    媲
    -0.63
     hazel
    -0.63
     quanto
    -0.63
     prevent
    -0.62
    Rook
    -0.62
    uffy
    -0.62
    POSITIVE LOGITS
     desert
    1.68
     Coachella
    1.63
     Desert
    1.61
    Desert
    1.51
     Palm
    1.44
    desert
    1.42
    Palm
    1.40
     Oasis
    1.16
     deserts
    1.14
     KES
    1.14
    Activations Density 0.014%

    No Known Activations